Y. Srinivas

A novel and generalized approach in the inversion of geoelectrical resistivity data using Artificial Neural Networks (ANN)

The non-linear apparent resistivity problem in the subsurface study of the earth takes into account the model parameters in terms of resistivity and thickness of individual subsurface layers using the trained synthetic data by means of Artificial Neural Networks (ANN). Here we used a single layer feed-forward neural network with fast back propagation learning algorithm. So on proper training of back propagation networks it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data with reference to the synthetic data trained in the appropriate network. During training, the weights and biases of the network are iteratively adjusted to make network performance function level more efficient. On adequate training, errors are minimized and the best result is obtained using the artificial neural networks. The network is trained with more number of VES data and this trained network is demonstrated by the field data. The accuracy of inversion depends upon the number of data trained. In this novel and specially designed algorithm, the interpretation of the vertical electrical sounding has been done successfully with the more accurate layer model.

Environmental applications of geophysical and geochemical methods to map groundwater quality at Tuticorin, Tamilnadu, India

Coastal aquifers can become polluted due to natural and human activities, such as intrusion of saline water, discharge of effluents in industrial areas and chemical weathering of natural geological deposits. The present study is aimed mainly at understanding the geophysical and chemical characteristics of groundwater near Tuticorin, Tamilnadu, India by studying the electrical resistivity distribution of the subsurface groundwater by applying the Schlumberger vertical electrical sounding (VES) technique followed by chemical analysis of water samples. A total of 20 VES soundings were carried out to understand the resistivity distribution of the area and 21 water samples were collected to analyze the chemical quality. The interpretation and analysis of the results have identified different hydrogeologic behaviors, a highly saline coastal aquifer and freshwater locations. The results obtained from geophysical and geochemical sampling are in good agreement with each other. The approach shows the efficacy of the combination of geophysical and geochemical methods to map groundwater contamination zones in the study area.

Wavelet denoising algorithm to refine noisy geoelectrical data for versatile inversion

This paper presents a denoising technique based on wavelet algorithm for inverting geoelectrical resistivity data. The presented work compares different denoising process by thresholding wavelet algorithm. Discrete wavelet transform is used to denoise the geoelectrical resistivity data. It is suitable for applying vertical electrical sounding data. The optimum performance is obtained and the result is investigated under several constraints. This method can be adopted to any geophysical data for pre-processing. Daubechies wavelet functions (‘db’) of different decomposition levels with four (“rigsure”,“universal thresholding”,“minimax”,“heursure”) thresholds were attempted and the significant reduction of noise is effectively done. The data is initially subjected to synthetic noisy data with various levels of signal to noise ratio (SNR) and tested results with optimum condition is implemented to the noisy field data which is verified with the nearby ground truth information. Error measures reveal that is algorithm is best suited for denoising the geoelectrical resistivity data.

An automatic inversion tool for geoelectrical resistivity data using supervised learning algorithm of adaptive neuro fuzzy inference system (ANFIS)

Estimation of subsurface parameters of earth need an efficient and knowledge based algorithm to enthrall the real world truth clearly. Implementing the adaptive neuro fuzzy inference system (ANFIS) is worthwhile in this case of non-linear parametric approach. The ambiguous property of the conventional inversion technique results can be prevailing over by implementing the soft computing tool. The coalesce behavior of neural networks logics and fuzzy sets with certain rule based logics will concise the inversion technique to obtain the preferred result. In the present study, ANFIS algorithm was applied in direct inversion approach and the most prominent of this approach is supervised learning techniques adapted in the algorithm specially to enroll the concepts of inverting the geoelectrical data in a systematic way. The subsurface parameters of earth are mysteriously identified by sounding or direct bore techniques. Sounding method in geophysics plays the prominent role in understanding the subsurface features of earth. But major part of the sounding method relies on inversion techniques. Since the data obtained from the earth is non-linear and heterogeneous it is difficult to estimate the parameters more clearly. Thus apart from using any conventional inversion techniques which are mainly focusing on initial model layer parameters. If the initial layer parameters are not given in the particular range, then the forward modeling solution tends dissimilarity of observed bore hole/litholog data. Thus direct inversion dominates in estimating the parameters with the help of soft computing inversion techniques. The proposed technique solves most of the subsurface problems since it depends on the trained knowledge. The supervised learning technique has been validated with Tuticorin and Kanyakumari coastal region data and found to be successful.

Tollgate neural networks (TNN) model with time bound learning methodology for futuristic approach in climatic data analysis

Recent advances in neural networks algorithm solve many complex problems in real world. Neural networks were applied to many non-linear prediction domains such as speech recognition, computer vision, machine learning and other areas. One of such challenging phenomena is applying neural networks to weather predictions and climate modelling. Because of its large size and complex data, it is difficult to predict. In this research work, climate factors were taken to make predictions using novel tollgate neural networks (TNN) algorithm. TNN algorithm is projected with quick training methodology rather than conventional approach. The advantage of this versatile model is that it can successfully incorporate the useful features by pruning the unnecessary data during training. Therefore it is intriguing algorithm to approach climatic patterns to predict certain notable variations in the area under study. Experimental results proclaim that this framework of the algorithm is efficient, adaptable and outperforms popular methods when tested on different climatic patterns. It also helps to form an proficient learning and optimisation platform for other large scale complex problems.

Geoelectrical data processing using neuro fuzzy pattern recognition scheme for unambiguous subsurface modelling

Geoinversion takes off different forms to assess the subsurface formations more noticeably. The evolution of soft computing inversion technique makes the geoinversion to the next level of modelling parameters. In this research work, the novel neuro fuzzy pattern recognition approach was introduced to solve the non-linearity involved in geoelectrical resistivity data for appraising the subsurface parameters. The novelty encompasses in generating the patterns using Artificial Neural Networks (ANN) for the geoelectrical resistivity data obtained from the Vertical Electrical Sounding (VES) data as well as the pattern recognition done by the Adaptive Neuro Fuzzy Inference System (ANFIS) algorithm is predominant in mitigating the near world truth information that is available. Moreover, the ambiguities of the principle of equivalence have been reduced further by incorporating the Dar-Zarrouk parameter evaluation of longitudinal conductance and transverse resistivity. Thus, this tool could be a good alternate for any conventional algorithm for unravelling such complex problems.

Forecasting groundwater vulnerability in the coastal region of southern Tamil Nadu, India—a fuzzy-based approach

This paper presents applied research on fuzzy logic modeling to forecast the distribution of salinity in the coastal region of southern Tamil Nadu, India. Geoelectrical resistivity data has been used in this research, apart from nominal approach of salinity forecasting using geochemical data analysis. The data collected using vertical electrical sounding (VES) method was fed as an input for fuzzy inverting algorithm to evaluate true resistivity and thickness of subsurface layers. Inverted resistivity values have been subjected to fuzzy rule-based approach for salinity forecasting. Classifications have been made on the basis of linguistic variables with five linguistic terms of resistivity range using a triangular membership function of fuzzy logic. The purpose is to find the saltwater intrusion in the coastal region of Tuticorin district, Tamil Nadu, India. This research work reveals that fuzzy logic would be the effective tool for solving complex problems as well as enhancement in integrating multiple features necessary for the study. The results overlain in the surrounding regions which were mapped the threatening zones; hence, to mark pre-awareness in the regions, more rainwater harvesting system and avoidance of human anthropogenic activities need to be implemented.

Geoelectrical Data Inversion by Clustering Techniques of Fuzzy Logic to Estimate the Subsurface Layer Model

Soft computing based geoelectrical data inversion differs from conventional computing in fixing the uncertainty problems. It is tractable, robust, efficient, and inexpensive. In this paper, fuzzy logic clustering methods are used in the inversion of geoelectrical resistivity data. In order to characterize the subsurface features of the earth one should rely on the true field oriented data validation. This paper supports the field data obtained from the published results and also plays a crucial role in making an interdisciplinary approach to solve complex problems. Three clustering algorithms of fuzzy logic, namely, fuzzy -means clustering, fuzzy -means clustering, and fuzzy subtractive clustering, were analyzed with the help of fuzzy inference system (FIS) training on synthetic data. Here in this approach, graphical user interface (GUI) was developed with the integration of three algorithms and the input data (AB/2 and apparent resistivity), while importing will process each algorithm and interpret the layer model parameters (true resistivity and depth). A complete overview on the three above said algorithms is presented in the text. It is understood from the results that fuzzy logic subtractive clustering algorithm gives more reliable results and shows efficacy of soft computing tools in the inversion of geoelectrical resistivity data.